© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 14275
    Prev
    Next
    INDEX
    Explanations

    abstract mathematical concepts related to transformations and actions in theoretical frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "mu" follows "2" or underlines

    np_acts-logits-general · gemini-2.0-flash

    2mu spacing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.56
     autorytatywna
    -0.51
    IntoConstraints
    -0.47
    AutoresizingMask
    -0.44
    SuspendLayout
    -0.43
     createState
    -0.42
    ThroughAttribute
    -0.42
    ItemBackground
    -0.41
    zonder
    -0.41
     pungkas
    -0.41
    POSITIVE LOGITS
     تضيفلها
    0.48
     canst
    0.43
    eradish
    0.43
     يتيمه
    0.42
    同樣
    0.42
    ंदीखरीदारी
    0.42
    同样
    0.42
    basicConfig
    0.42
    +:+
    0.40
    ImageIO
    0.40
    Activations Density 0.429%

    No Known Activations